© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 38342
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and their associated actions or intentions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Agents
    -0.08
    unately
    -0.07
    irut
    -0.07
     Luck
    -0.07
    ãĥ©ãĥĥãĤ¯
    -0.07
    illance
    -0.07
    acier
    -0.07
    uckles
    -0.07
    ÄĽj
    -0.07
    ahat
    -0.07
    POSITIVE LOGITS
     will
    0.12
    will
    0.10
    'll
    0.09
    ’ll
    0.09
     sẽ
    0.09
     akan
    0.07
     bÄĻdzie
    0.07
    å°±ä¼ļ
    0.07
    æľĥ
    0.07
    ä¼ļ
    0.07
    Activations Density 0.024%

    No Known Activations